【11月1日 更新分】機械学習に関する論文まとめ

11月1日に公開された論文


ニューラルネットワーク

Learning Graph Convolution Filters from Data Manifold
著者:Guokun Lai, Hanxiao Liu, Yiming Yang
Statistical Speech Enhancement Based on Probabilistic Integration of Variational Autoencoder and Non-Negative Matrix Factorization
著者:Yoshiaki Bando, Masato Mimura, Katsutoshi Itoyama, Kazuyoshi Yoshii, Tatsuya Kawahara

自然言語処理

Unsupervised Machine Translation Using Monolingual Corpora Only
著者:Guillaume Lample, Ludovic Denoyer, “MarcAurelio Ranzato”
Keyword-based Query Comprehending via Multiple Optimized-Demand Augmentation
著者:Boyuan Pan, Hao Li, Zhou Zhao, Deng Cai, Xiaofei He
Neural Wikipedian: Generating Textual Summaries from Knowledge Base Triples
著者:Pavlos Vougiouklis, Hady Elsahar, Lucie-Aimée Kaffee, Christoph Gravier, Frederique Laforest, Jonathon Hare, Elena Simperl

画像解析

Guarding Against Adversarial Domain Shifts with Counterfactual Regularization
著者:Christina Heinze-Deml, Nicolai Meinshausen
PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes
著者:Yu Xiang, Tanner Schmidt, Venkatraman Narayanan, Dieter Fox
Improving Object Localization with Fitness NMS and Bounded IoU Loss
著者:Lachlan Tychsen-Smith, Lars Petersson
Segmentation-by-Detection: A Cascade Network for Volumetric Medical Image Segmentation
著者:Min Tang, Zichen Zhang, Dana Cobzas, Martin Jagersand, Jacob L. Jaremko
Countering Adversarial Images using Input Transformations
著者:Chuan Guo, Mayank Rana, Moustapha Cisse, Laurens van der Maaten
Semantic Image Retrieval via Active Grounding of Visual Situations
著者:Max H. Quinn, Erik Conser, Jordan M. Witte, Melanie Mitchell
Image Patch Matching Using Convolutional Descriptors with Euclidean Distance
著者:Iaroslav Melekhov, Juho Kannala, Esa Rahtu

音声解析

Speaker Diarization with LSTM
著者:Quan Wang, Carlton Downey, Li Wan, Philip Andrew Mansfield, Ignacio Lopez Moreno
User Environment Detection with Acoustic Sensors Embedded on Mobile Devices for the Recognition of Activities of Daily Living
著者:Ivan Miguel Pires, Nuno M. Garcia, Nuno Pombo, Francisco Flórez-Revuelta
Full-info Training for Deep Speaker Feature Learning
著者:Lantian Li, Zhiyuan Tang, Dong Wang
Seeing Through Noise: Visually Driven Speaker Separation and Enhancement
著者:Aviv Gabbay, Ariel Ephrat, Tavi Halperin, Shmuel Peleg

強化学習

TreeQN and ATreeC: Differentiable Tree Planning for Deep Reinforcement Learning
著者:Gregory Farquhar, Tim Rocktäschel, Maximilian Igl, Shimon Whiteson
Visualizing and Understanding Atari Agents
著者:Sam Greydanus, Anurag Koul, Jonathan Dodge, Alan Fern
Regret Minimization for Partially Observable Deep Reinforcement Learning
著者:Peter H. Jin, Sergey Levine, Kurt Keutzer
Modeling Attention in Panoramic Video: A Deep Reinforcement Learning Approach
著者:Yuhang Song, Mai Xu, Minglang Qiao, Jianyi Wang, Liangyu Huo, Zulin Wang

無料メールマガジン登録

週1回、注目のAIニュースやイベント情報を
編集部がピックアップしてお届けしています。

こちらの規約にご同意のうえチェックしてください。

規約に同意する